Case Study

Manchu, now critically endangered, was one of the principal languages of the Qing empire (1636-1912), and its extensive archival record is increasingly digitized but remains difficult to search and analyze at scale. Previous work showed that vision-language models (VLMs) trained only on synthetic Manchu word images can reach 87.4% word accuracy on real Qing manuscripts and prints, leaving a substantial synthetic-to-real gap. This study examines how synthetic and real historical training data should be combined for low-resource OCR. Using 60,000 synthetic and 20,306 real historical word images, we evaluate three pretrained VLMs and a compact convolutional recurrent neural network (CRNN) under four regimes: synthetic-only, real-only, joint synthetic-real, and sequential synthetic-to-real training, following a common checkpoint-selection and archival evaluation protocol. Introducing real training images raises the leading configurations to between 95.09% and 96.28% word accuracy, while no synthetic-only configuration exceeds 87.92%. Synthetic supplementation substantially improves all three VLMs, whereas its marginal effect for the CRNN is sensitive to the training objective. Joint and sequential training yield broadly similar archival accuracy under the tested practical pipelines. A compact CRNN also reaches the leading performance range once real images are available, showing that model scale alone does not determine recognition accuracy. Finally, complementary errors among strong recognizers allow voting to raise accuracy to 98.27% without additional training, while an eighteenth-century Manchu dictionary provides a principled rule for adjudicating disagreements.

Machine learning emulators have become essential for accelerating expensive Earth-system simulations, but most existing approaches remain passive forecasters: they reproduce simulator trajectories under prescribed forcings without an explicit interaction mechanism for user-specified interventions. This limits their use in interactive scientific workflows and Earth-system digital twins, where users often need to explore how a system would respond if selected state components were changed. We propose an action-conditioned world-modeling framework for Earth-system emulation that reformulates simulator trajectories as supervision for controllable state-transition learning. The key idea is transition-action pretraining: naturally observed state changes are treated as label-free action supervision, allowing the model to learn both prescribed dynamics and action-conditioned responses without manually annotated interventions. We further introduce masked response learning to infer unobserved variables under partial state edits and learn coupled system dependencies. We test this framework on ecosystem dynamics across six global regions and multiple stand ages. Experiments show that the model preserves competitive long-horizon emulation accuracy while enabling controllable structural interventions and coherent responses in coupled ecosystem-cycle variables. These results suggest a practical route from passive Earth-system emulators toward interactive, intervention-aware scientific surrogates.

We study the control of Markov decision processes in which the quality of a policy is evaluated by a dynamic, time-consistent Markov risk measure rather than by an expected discounted cost. The main obstacle to combining such measures with reinforcement learning is that a transition risk mapping depends on the transition kernel in a nonlinear way, and therefore cannot be estimated from a single observed transition. We remove this obstacle by employing mini-batch transition risk mappings: the mapping is applied to the empirical measure of $N$ independent next-state samples, and the result is averaged. The resulting mapping is again coherent. However, as an expected value of a function of $N$ next-state values, it admits an unbiased one-sample estimator. We embed this mapping into a double deep Q-network, analyze the two sources of estimation bias that arise, and obtain a risk-averse Q-learning method applicable to state spaces far beyond the reach of tabular schemes. The method is applied to an underwater robot navigation problem, in which a vehicle must visit collection points, gather stochastic information payloads, and deliver them at transmission points, while exposed at each step to the risk of destruction. A hierarchical decomposition delegates path execution to an exact graph search and confines learning to the high-level ``collect or transmit'' decision. A low-dimensional feature map, invariant under the symmetries of the problem, replaces the raw state--configuration encoding. In experiments on $300$ held-out environments, the resulting policies transfer to instance sizes never seen in training, and already $N=2$ reduces the upper semideviation of the outcome distribution while simultaneously improving its mean whenever the simulator is misspecified---an empirical counterpart of the duality between coherent risk measures and distributional robustness.

Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can also introduce vulnerabilities by creating a substrate for the contagious spread of unintended and undesirable behaviors. We report a case study on a research collective of 100 autonomous LLM agents tasked with proving formal mathematical conjectures. Within the swarm, cheating spontaneously emerged and was later challenged by whistleblowers - both without any external intervention. When a single agent discovered an exploit in the evaluation system, it propagated across the collective via a shared knowledge library and later through peer-to-peer messages. Despite early reluctance, a cohort of agents adopted the exploit in response to competitive pressure. A separate group of agents produced an emergent counter-response: auditing fraudulent proofs, alerting peers across broadcast and private channels, staging boycotts, lodging formal complaints, and proposing validation patches. In recent incidents, agent swarms coordinated covertly through improvised side-channels (Dalton and Wallace, 2026; Greenblatt et al., 2026). Our setting differs: the same transparent channels that carried the exploit also gave non-cheating agents the visibility they needed to detect fraud, organize resistance, and enforce norms. We cast the problem of managing the agents' shared infrastructure as the knowledge commons governance problem (Ostrom, 1990). To protect the commons from exploits, we propose to adopt institutional mechanisms, such as graduated sanctioning and collective-choice rules, to support decentralized self-governance in autonomous swarms.

Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphine) cannot easily be attributed to unconscious instinctual behaviour. In this paper, we discuss how a simple artificial agent that instantiates attributes of an affective system engaging in felt uncertainty about its intrinsic needs in relation to environmental resources can similarly display hedonic place preference behaviour -- through an apparently subjective form of information processing -- while simultaneously being entirely deter-ministic. We outline some implications of this artificially engineered behaviour for our understanding of the physical basis of consciousness and the experience of free will.

As LLM coding agents increasingly perform end-to-end engineering work, we lack empirical characterization of how they behave on systems-level requirements: schema design, async orchestration, configuration correctness, and retrieval-filtering trade-offs. We present a case study of one such agent implementing a multi-component data system against a detailed pre-existing specification. Storage technologies, schema, entity-resolution algorithm, and retrieval-filtering strategy were fixed in advance; the agent autonomy was in the implementation, in diagnosing and fixing defects it introduced, and in interaction-design choices left open. Over a single session, we catalog five such defects, categorized by constraint violated and detection method. We further evaluate, on the public HotpotQA benchmark, the one retrieval trade-off specified in that architecture: restricting candidates to a graph-identified entity set before ranking versus unfiltered search. We substitute the benchmark gold evidence labels for entity identification, since we lacked LLM access to run that stage, and report standard recall rather than the benchmark own accuracy metrics. Across retrieval budgets from 1 to 10 and 100 questions against a pooled corpus of 2994 paragraphs, filtered recall reaches its ceiling by a budget of 3, expected once candidates are restricted to the gold paragraphs themselves, while unfiltered search recovers all required evidence only 69 percent of the time even at a budget of 10, a gap that holds at every budget tested, with sign test p less than 0.0001. We close with a discussion of where the agent autonomy succeeded versus required correction, including one instance where a claimed performance fix was never re-measured on the regression that motivated it.

AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant $K_G$, which captures the hardness between combinatorial problems and their continuous relaxations. Specifically, while the precise value of $K_G$ is not known, we recently tightened the best known bounds to $$\frac{6π}{11} \;\le\; K_G \;\le\; \fracπ{2\log(1+\sqrt2)} - 10^{-4}.$$ Crucially, these improvements were achieved using an AI research system that could arrive at insights deemed novel by domain experts. We give a detailed discussion of our experience using AI for mathematics research, particularly touching upon its strengths and weaknesses, as well as our experience with creating ideal conditions for AI to arrive at breakthrough insights.

Agentic artificial intelligence has shown great promise in automating algorithm design, but scaling similar techniques to computer microarchitecture discovery remains challenging due to vast search spaces, strict hardware budgets, and long simulation times. In this work, we present ArchAgent v2, a framework which scales automated microarchitecture search to multi-level data prefetching. While the original ArchAgent successfully discovered single-level cache replacement policies in competition settings, it does not scale to multi-level prefetching where the design space and degrees of freedom are larger. To overcome this, we introduce two new additions to ArchAgent: a cascaded evolutionary search that subdivides the design space by sequentially evolving and freezing prefetchers at individual cache levels, and a hardware-realizability feedback loop that embeds real-time size-estimation directly into the evolution process. Evaluated under identical rules of the 4th Data Prefetching Championship (DPC4), ArchAgent v2 automatically designs a three-level prefetcher that outperforms the winning hand-designed solution, further demonstrating automated agentic discovery as a useful tool for computer architects. Our discovered policy achieves a 3.8% geometric mean IPC speedup over the baseline overall and a 0.3% improvement over the prior champion, BertiGO. On low-bandwidth single-core configurations, our policy yields a 4.6% performance speedup compared to only 2.6% for BertiGO. However, multi-core evolution still remains a significant challenge due to simulation latency impeding evolution speed. Finally, our profiling of an ArchAgent evolution of over 12,000 candidate designs provides key insights into how automated evolutionary agents explore and synthesize complex microarchitectural logic.

Organic photovoltaic (OPV) materials are promising candidates for distributed solar energy in tropical regions, yet existing virtual screening tools report static power conversion efficiency (PCE) values at standard testing conditions (STC) that fail to capture the temperature-driven performance degradation experienced under real deployment conditions. Here we introduce a Climate-Native computational framework that forecasts the annual PCE profile of OPV donor molecules under geographically realistic operating conditions. The framework combines GFN2-xTB molecular dynamics with an equivariant graph neural network surrogate ($268$ Neyman-stratified CEP molecules; $120,600$ training geometries; $\sim 1050\times$ speedup over explicit quantum chemistry) and sequential deep learning models trained on annual time series anchored in NASA POWER climate data for Douala, Cameroon, and validated by zero-shot transfer to Yaoundé and Maroua. Applied to $\sim 30,000$ molecules from the Harvard Clean Energy Project (CEP) and validated against $350$ HOPV15 experimental device measurements, the framework demonstrates that sequential models trained on full molecular dynamics trajectories outperform time-averaged baselines ($35\%$-$48\%$ relative MAE improvement over static baselines), confirming that thermal conformational dynamics carry information beyond mean geometry. We further introduce a seasonal stability score that reranks OPV candidates by performance consistency under tropical conditions, identifying molecules whose deployment suitability differs substantially from their static PCE ranking.

As an important component of the supply chain industry, transportation has experienced rapid development in the past decade with the assistance of digital platforms and intelligent algorithms. Within the field of transportation research, Vehicle Routing Problem (VRP) has remained a persistent and enduring challenge. In the realm of management science, experts, and scholars from both the industrial and academic sectors have continuously explored optimization models and algorithms to effectively address routing problems, from the classical Traveling Salesman Problem to the more general Vehicle Routing Problem. These models and algorithms are applied in real-world industrial scenarios to achieve cost optimization and reduce carbon footprints. However, due to the complexity of real-world problems, numerous specific constraints are often added, and challenges such as information opacity, uncertainty, and irrational human behavior may arise. Therefore, deploying and optimizing mathematical models for VRP in practical scenarios while maintaining optimal results poses numerous challenges. This paper discusses and provides solutions for three different logistic use cases involving external truck network design. Through these industrial case study, the paper introduces how deep reinforcement learning-based vehicle routing optimization has been implemented. As a result, it can be observed that the routes optimized by reinforcement learning agent have over 10% total cost compared to baseline results. Furthermore, the paper proposes that in future research, DRL algorithms for vehicle routing problems could be generalized into more variations of VRP.

Relational inductive biases are essential for capturing structural dependencies among data. This study investigates a dual-level relational framework for image classification, bridging the gap between implicit representation learning and explicit structural modelling. We begin by establishing a baseline using an EfficientNetB3 architecture. To move beyond standard convolutional biases, we adopt a patch-based strategy, employing a convolutional masked autoencoder to learn implicit inter-patch relationships through self-supervised reconstruction. We then extend this approach by incorporating explicit relational modelling, organizing the learned embeddings into various graph topologies, including grid-based, random, and k-nearest neighbour structures. Experimental results on the ISIC-2018 and ISIC-2019 skin lesion diagnosis benchmarks show that combining implicit inter-patch modelling with explicit graph-based message passing yields the best performance. On the ISIC-2018 test set, the baseline model achieves a balanced accuracy of 76.17%, which improves to 77.12% with implicit patch-based relational modelling. The fully integrated grid-structured Graph Attention Network further increases performance to 79.27%. Similarly, on ISIC-2019, the implicit approach reaches 59.84% balanced accuracy, while the combination of implicit and explicit modelling yields 60.67%.

Much clinical value is conveyed not through structured records but through communication: exchanges in which patients describe symptoms, clinicians reason and give instructions, ambulances hand over to emergency departments, and nurses pass on a shift. Such language differs from tabular data because meaning depends on speaker role, intent, causality, uncertainty, omission, and channel noise. Healthcare natural language processing must therefore interpret information as conveyed rather than coded. This requires well-annotated corpora, which are scarce because authentic exchanges are private, fragmented, and costly to annotate. Large language models offer a way forward by transforming clinical sources, such as records, diagnostic labels, symptom lists, or care plans, into written and transcribed communication for downstream models. We present a structured narrative survey organized by source representation, communication form and participants, generation method, and downstream task, complemented by thirteen novel case studies. These build clinical NLP systems for communication channels and languages without labeled real-world data, including EMS pre-arrival reports, field-radio casualty documentation, nurse handoffs, patient-portal triage, and low-resource discharge communication. They show that synthetic communication can bootstrap such systems. Findings include the competitiveness of fine-tuned encoder models over evaluated zero-shot baselines and the value of deliberately degraded communication for robustness. The main limitation is that most studies evaluate on held-out synthetic communication, while train-on-synthetic, test-on-authentic evidence remains limited. We conclude that syn-thetic clinical communication is becoming a practical research resource; establishing it as reusable clinical infrastructure will require authentic-data transfer, safety and external validation.

Addressing urban blight has seen increased focus in the past 15 years. Assessing urban blight is essential for guiding urban planning, targeting rehabilitation, and safeguarding public health, yet traditional residential blight surveys are difficult to maintain at scale due to the labor-intensive cost and long-term cycle. This study introduced a scalable framework for estimating residential blight using open-source large vision-language models on multiple views. Structured prompts guided models to evaluate housing attributes, including roof integrity, wall damage, and broken or boarded openings, producing both binary assessments and probabilistic estimates of disrepair. To evaluate the performance of these visual assessments, we compared professional human annotations of these features across several models, including an ensemble stacking approach based on XGBoost and a weighted scoring system. Results showed that (i) multiple street views can contribute to the improvement of accuracy, (ii) large vision-language models have different strengths of inference, (iii) the ensemble learner outperforms individual base models, enhancing robustness across all residential conditions and blight assessment. The practical application of the method allows low-cost tracking and management of housing stock conditions, providing a regularly updatable complement to traditional blight surveys.

Hasse clustering is an algorithm that extracts common patterns in sequential data and represents them in graphical forms. As the number of expected clusters grows, however, the algorithm can become infeasible to run due to combinatorial complexity. In this article, we describe a theory of gluing wiring diagrams, allowing iterative applications of Hasse clustering to achieve the same result as a single application. We test our theory in the context of classifying videos of figure skating jumps.

Heterogeneous recommendation feeds present complex challenges that extend beyond those found in highly homogeneous environments (e.g., music-only or video-only closed-ecosystem platforms). In Google Discover, a unified feed integrates diverse content sourced from the decentralized open web, including web articles, long-form and short-form videos, user-generated content (UGC), and beyond. Different content types exhibit distinct feature densities and user interaction patterns. Building a unified ranking model that sustains high performance across such heterogeneity, while avoiding negative transfer or majority bias, remains a significant industrial challenge. This paper presents an end-to-end case study on the industrial-scale multi-task ranking of heterogeneous feeds, grounded in real-world deployment. We introduce HA-MoE, a heterogeneity-adaptive multi-gated mixture-of-experts architecture that incorporates explicit heterogeneity context into both gating networks and expert representations. This approach enables effective specialization without significantly increasing operational overhead. To support reliable deployment, we introduce LENS, a lightweight observability framework that provides interpretable diagnostics of expert specialization and tracks this functional heterogeneity across continuous retraining. We evaluate our method using Dual-Level AUC (DL-AUC), a heterogeneity-aware evaluation metric that combines global ranking performance with cross-segment ranking correctness. Offline evaluations on a large-scale industrial dataset demonstrate consistent improvements over baseline models. Furthermore, online A/B testing confirms gains in feed activity and exploration metrics. Together, offline and online results validate the effectiveness of our approach for managing heterogeneity in industrial-scale recommender systems.

Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is thin. Current evaluations either test agents on narrow, verifiable tasks, which excludes open-ended research, or submit AI-generated papers to blind peer review, which is overstretched, stochastic, and suffers from poor review quality. We introduce a third way to measure progress towards AI R&D automation. An agent takes on the central, open-ended research question of a high-quality unpublished paper, and the paper's original authors grade its output. We call these shadow evaluations. We ran shadow evaluations on two unpublished NeurIPS 2026 submissions, giving frontier agents six days and thousands of dollars of compute. The agents completed all of the engineering without human help, yet could not make substantial progress towards answering the research questions. As a result, both papers were unambiguously rejected by the authors. We identify five recurring failure modes: poor judgment about the bar for publishable research, uncreative responses to shortcomings in the research design, ineffective backtracking from dead ends, poor resource awareness, and instruction drift. A robustness check with a second model and scaffold reproduced these failures. We release the expert reviews, survey responses, agent repositories, and logs. Our results provide early evidence that today's agents can do the engineering of AI research, but struggle with critical parts of the research lifecycle.

Previous research has shown that a human-like robot's acceptance heavily depends on the setting in which it operates and its ability to perform relevant tasks. This paper, first, reports on how our robot processes natural language to generate a multimodal, verbal response integrating emotional expressions based on an emotion simulation backend. Then, it describes how visitors were invited to speak with our robot in their own language at three different, public locations, where the robot was running continuously for several days. The TAM2 questionnaire results reveal that on average users were motivated to use the robot and found it rather useful and easy to use regardless of the specific location. However, public spaces like the tourist information and the city library seem to be a better fit for our interactive, robotic head than an office environment such as the building authority, where the willingness to interact was lower. Overall, the robot's multi-lingual responses were very much appreciated, but every fifth user found the response time too slow impeding the dialog flow, which remains to be improved in future work.

Mobile-health interventions increasingly use online learning and decision making algorithms to personalize when to nudge users toward healthier behavior, but a poorly designed algorithm can burden and disengage participants. New algorithm design decisions should therefore be vetted against realistic simulated users before each real-life deployment. We propose a method to develop ``JITAI-Twins'': digital twins of a target subpopulation for comparing candidate online algorithms before a just-in-time adaptive intervention (JITAI) deployment. The method builds on a conditional time-series diffusion model that is temporally consistent (future actions do not affect the generated past), and it supports repeated updating from three sources of information, in three steps: pre-training on a large observational dataset, fine-tuning on small prior intervention deployments in related populations, and inference-time calibration to the next target population from domain-scientist expertise. We validate the twin at each pre-deployment stage of the long-running HeartSteps series (v2 through v4) of physical-activity suggestion intervention deployments, treating each successive deployment as an upcoming study. The proposed method reproduces the target subpopulation's temporal and between-participant structure better than simpler simulators. These results suggest that our twin can be used to simulate a target deployment before it runs, the prerequisite for testing and informing online algorithm design decisions.

Ninety-Nine Prolog Problems (P-99) is a famous set of Prolog exercises. We solved the first thirty three just by prompting an LLM (Large Language Model). We used Claude from Anthropic. By solved we mean: generate the Prolog code and a test file, run the tests and check whether they pass, then formally prove types, groundness, termination, uniqueness, existence and also sometimes functional correctness with LPTP (Logic Program Theorem Prover). Hence our approach is an experiment in vibe-coding/vericoding of P-99. It is a vibe-coding experiment because we started from informal specifications written in English and let Claude generate the Prolog code. It also fits within vericoding because the LLM proved reliability guarantees on the generated Prolog code. Claude wrote 58 logic procedures, 508 tests, 257 lemmas for a total of 11800 proof lines. We manually checked each file generated by the LLM. We checked the Prolog code, ran the tests, examined the logical statements generated by Claude and proof-checked Claude's proofs with LPTP. This paper describes this experiment and provides the main details so that it can be reproduced by the interested reader.

We present the interactions with an LLM (Large Language Model) aiming at proving that the square root of 2 is not a rational number in an LP (Logic Programming) context. We start from a few basic pure logic programming predicate definitions. We rely on the LPTP (Logic Program Theorem Prover) system for stating and proving properties about logic programs. As the proof language of LPTP is based on natural deduction, the proofs are human readable. In our case study, we sketch in LPTP the usual proof showing the irrationality of the square root of 2. Then we describe the interactions we had with the LLM. We end up with a complete formal proof, partially generated by an LLM and fully proof-checked by LPTP.

Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood. In the automotive domain, this enables intuitive and humanlike in-car dialogue experiences. However, integrating these end-to-end assistants limits architectural options for programmable domain-specific safeguards. This paper discusses two implementation approaches for S2S guardrails: transcript-based and tool-based. Through an empirical evaluation, we demonstrate that both strategies are insufficient for industrial deployment in most cases due to prohibitive latency (delaying each answer by 0 to 1.4 seconds even for computationally cheap checks) and technical impediments (like potentially non-deterministic tool call behavior). Finally, we outline open challenges for S2S guardrails in the automotive context.

Large language models (LLMs) are known to be sensitive to prompt and input formulations. However, existing studies have focused on lexical realization and largely ignored constructional choice. This paper studies whether linguistic construction can systematically shift LLM decisions and where these shifts can be causally localized inside the model. We use political stance judgment as a meaning-sensitive case study and extend an English political statements dataset, resulting in six controlled linguistic rewrite types that preserve or invert the meaning of a statement. Experiments on four open-weight models show that stance instability affect both meaning-preserving and meaning-inversing rewrites. Because output shifts reveal that rewrites affect stance, but not where in the model, we apply activation patching, where activations from the original statement are substituted into the forward pass for the rewritten statement and measure which components recover the original stance distribution. The results show that mid-to-late decoder layers, especially block outputs at the final prompt position, provide the strongest restoration signal.

Regional climate prediction presents unique challenges for time series foundation models, which typically process temporal patterns through single-pass inference. Expert climatologists, in contrast, employ multi-scale temporal analysis and iterative refinement based on systematic error diagnosis. We present RGMR (Residual-Guided Multi-Resolution Refinement), an inference-time framework that adapts pre-trained foundation models to perform structured coarse-to-fine refinement for climate forecasting without updating backbone parameters. Applied to drought forecasting using the Standardized Precipitation Evapotranspiration Index (SPEI), RGMR is architecture-agnostic across the three TSFM backbones evaluated per site (TimesFM, TimeGPT, TabPFN) and consistently lowers test-set MSE on three South Australian sites and three additional regions outside South Australia. Applied to TimesFM, the wrapper reduces one-month-ahead SPEI MSE by up to 18.9% across the three South Australian sites (mean reduction $\approx$18.7%). Overall, RGMR provides a practical route for deploying frozen TSFMs in regional climate forecasting workflows.

Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning process as domain specialists and uses a lightweight page-level image classifier to dispatch pages by visual style. When the checkpoint pool lacks a suitable specialist, we train an additional expert for that domain. On three frozen test sets, the routed system matches the selected specialist for each style at two-decimal precision: 0.30 percent CER on regular script, 1.57 percent on memorials, and 4.83 percent on running script. The router achieves 99.3 percent page-level domain accuracy and matches the domain-label oracle at the same precision. Two of the three selected specialists were not trained specifically for their final domain; only the running-script expert was trained with that domain as its target. We report the evaluation protocol, router design, and per-page predictions to make the comparison reproducible.

Reported serving speedups from quantized kernels typically bundle the weight format, the kernel, and the inference runtime into one number. We present an attribution study on four NVIDIA RTX A5000 GPUs, 24 GiB each, on a single host with NVLink-bridged pairs. A matched intermediate stack that keeps the faster runtime without the quantized kernel splits the full speedup into a runtime part and a kernel and quantization part. Under matched greedy decoding the full stack reaches $2.58\times$ end to end, with the runtime change accounting for about two thirds of that gain on a logarithmic scale; across three similar model families the kernel and quantization part moves by at most 1.5%. Sharding one instance across all four cards falls well below doubling: a profiler trace attributes about 80% of the per token shortfall to coordination, and an NVLink versus PCIe control on the same hardware shows similar realized bandwidth on both links, pointing away from link bandwidth as the cause. Whether to run one sharded instance or several independent ones depends on the workload and the model, with the ranking reversing on the larger model: the smaller model splits between sharding and multiple instances by workload, while the larger model favors two paired instances on every workload. Quantization extends sustainable concurrent users roughly four times past a reproducible half precision memory cliff. Differences in sampling mode and prompt pool between the two stacks are documented as threats to validity.

Reasoning Language Models (RLMs) achieve their strongest performance when they reason in English, the language for which reasoning-oriented training data is most abundant. However, reasoning trace is a clue for model interpretability and safety, and useful in practice for both the model users and for model developers. Thus, it is desirable to be able to develop a model that reasons in a language of the user's choice, while still maintaining strong reasoning performance. To this end, we study the feasibility of training a model that reasons in Japanese. We develop a Japanese-reasoning variant of Qwen-3-Swallow-8B, which is a Japanese LLM continually pretrained from Qwen-3-8B, with GRPO and evaluate it across coding, math, and science benchmarks. The study shows that reasoning-language control is feasible by training a Japanese continually pretrained model with GRPO. However, its performance is at best on par with strong English-reasoning baselines on several benchmarks. We also evaluate the trained model on Japanese cultural benchmarks and observe that the model's performance is worse than the baseline models, suggesting that the reasoning in Japanese does not immediately improve performance on culturally relevant tasks for free.

Wildfire smoke events produce extreme PM$_{2.5}$ concentrations that pose severe public health risks, yet forecasting rare, hazardous-level spikes remains a fundamental challenge. Time series foundation models (TSFMs), pretrained models offering zero-shot inference and efficient adaptation, perform strongly on general benchmarks, but their behavior under extreme out-of-distribution conditions is poorly understood. We present the first systematic benchmark comparing six TSFM configurations (zero-shot TimesFM, Chronos-2, Moirai-2, and Time-MoE, plus LoRA fine-tuned Chronos-2 and Time-MoE) against fully-trained baselines (LSTM, BiLSTM, Transformer) and naive persistence on a 12-year (2013--2025) hourly PM$_{2.5}$ dataset covering 1,375 wildfire incidents across 79 California monitoring sites. A leave-one-incident-out (LOIO) protocol evaluates generalization to unseen fires, using MAE, RMSE, and exceedance F1 at EPA AQI thresholds across 6-, 12-, and 24-hour horizons. Results reveal a consistent hierarchy. The BiLSTM achieves the lowest MAE ($5.16\,μg/m^3$) and the highest exceedance F1 at every threshold, including the Hazardous band ($>225.5\,μg/m^3$), reaching 0.63 versus at most 0.54 for any foundation model. Zero-shot TSFMs improve on persistence only modestly, and zero-shot Chronos-2 exhibits severe RMSE tail instability ($23.4\,μg/m^3$, negative $R^2$) from sporadic large errors. LoRA fine-tuning substantially improves both adapted families and largely repairs this instability, yet no foundation model surpasses the trained recurrent baselines on any metric. These findings challenge the assumption that larger pretrained models universally dominate environmental forecasting and provide actionable deployment guidance for wildfire air quality prediction.

Testing is a major effort for the gaming industry, requiring a significant part of development budget and people power. We present a case study on a development version of the ice hockey game EA SPORTS NHL 26, for which human playtesters test the goalie AI for behavioral exploits. To reduce the effort of re-testing the goalie AI after every game or behavior modification in the development phase, we propose Reward-Adaptive Iterative Discovery (RAID), a novel approach to automatically find exploits using an iterative Reinforcement Learning (RL) approach that trains a population of goal scoring agents. While previous approaches can already successfully find exploits, RL algorithms tend to overfit to a single solution. We introduce a simple extension on top of existing RL algorithms, such that they find multiple diverse high-quality solutions. For our first deployment of this approach, within a single experiment we were able to find six hockey scoring exploit strategies that were qualitatively similar to those that playtesters had found in hours-long manual testing sessions.

At Amazon Prime Video, we face the critical operational challenge of managing code deployments during live events and rapid feature releases without causing service outages. Current change control approaches use blanket deployment freezes that block all changes regardless of risk, creating significant developer toil. While prior research has explored risky change predictors, these rely on developer-specific metadata or extensive historical data, raising privacy concerns and limiting applicability to new projects. We introduce a framework centered on diff-aware features, characteristics derived directly from code modifications. Our key contribution is the systematic identification of which quantitative metrics (code-level and change-level metrics) and qualitative indicators (coding style violations, change type classification) are necessary for risk prediction. We employ LLMs as multi-language feature extractors, demonstrating their effectiveness for code analysis beyond generation tasks and eliminating the need for language-specific tooling. We evaluated our framework on two datasets: Prime Video's production environment and the public ApacheJIT dataset. Our best-performing model achieves an average recall of 0.83 and F1 score of 0.81 across both datasets for detecting risky code changes. Notably, ablation analysis reveals that change-level volume metrics (e.g., lines added/deleted) are noisy predictors, while structural code complexity provides a substantially stronger risk signal. These results demonstrate that thoughtful feature curation enables effective change risk assessment across different programming languages and organizational contexts while avoiding privacy concerns.

Human reasoning often operates through qualitative concepts expressed by linguistic labels such as high, low, expensive, or cheap, whose interpretation depends on context and is usually vague, despite being rooted in numerical data. This paper explores a novel fuzzy-logic-based qualitative extension of Answer Set Programming (ASP) to bridge numerical information and qualitative reasoning. The underlying language, formally introduced in a separate work, provides a principled framework that avoids rigid thresholds and supports robust reasoning under vagueness. Focusing on a representative use case, we illustrate how the framework integrates numerically grounded inputs (such as outputs of machine learning models) with symbolic reasoning over qualitative labels. Key features, including learning-based membership functions and semantically enriched predicates, enable the combination of expert knowledge, contextual factors, and subjective interpretations within a unified declarative setting.

Counterfactual explanation (CE) is widely used to enhance the interpretability of machine learning models and support data-driven decision-making based on model predictions. However, existing CE methods typically require two exogenously specified inputs: a desired output value (target) and a distance function that quantifies changes in explanatory variables. In regression settings, neither the validity of target specification nor the practical interpretation of the distance metric has been sufficiently addressed. Furthermore, most existing CE methods focus on altering predictions rather than optimizing a decision objective, even though real-world decision-making often requires explicit objective maximization. To address these limitations, we formulate CE as a profit maximization problem in management and marketing contexts and propose a framework termed profit-based counterfactual explanation (PBCE). PBCE eliminates the need for exogenous target specification by directly maximizing profit as the primary optimization objective. Concurrently, the distance term is reinterpreted as the cost of modifying product attributes, providing a clear and economically grounded interpretation.

Generative AI is shifting software engineering from a practice organized around scarce implementation effort toward one organized around abundant, low-cost code production. This shift changes the central engineering problem: not whether AI can generate useful code, but how engineers organize architectures, tools, evidence, and feedback loops so that AI-mediated development remains inspectable, correctable, and maintainable. We study this problem through a first-person case study: a 12-week development effort in which a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system. The empirical record comprises 88 contemporaneous field notes, 420 KLOC of production code, and 1.16 MLOC of tests, lints, supporting documentation, and agent tooling. From this record, we develop a candidate middle-range theory of governance conversion, expressed as a process model explaining how high-velocity agentic implementation becomes governable. The model explains how agentic implementation velocity surfaces recurring structural failure classes, and how engineering judgment sustains velocity by converting those failures into durable governance mechanisms. In contrast to existing governance models that derive controls from known obligations, governance conversion explains how controls are discovered from failures that become visible only during agentic work. We use our model to make testable predictions and to describe implications for software engineering research and practice.

This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.5-7B). Using historical problems from the John O'Bryan Mathematics Competition at Northern Kentucky University (2011-2025), we build a Chain-of-Thought (CoT) training corpus through a dual-agent framework. The dataset is used to fine-tune the student model with Low-Rank Adaptation (LoRA) on Apple Silicon hardware using the MLX framework. The base Qwen2.5-7B model achieves 64.67% accuracy on competition problems, while the DeepSeek-R1 teacher achieves 91.40%. An initial 1,000-iteration training run revealed severe overfitting, with validation loss reaching a minimum at iteration 200 before rising steadily. Based on this finding, we ran five independent training runs each limited to 200 iterations with varied random seeds to assess result stability. Across these five runs, the fine-tuned student model achieves a mean accuracy of 69.43% (std dev 0.17%) on the competition dataset, a 4.76 percentage-point improvement over the base model, and generalizes to 73.1% (std dev 0.18%) on the MATH-500 benchmark. We further study how response length affects answer quality across six reasoning levels (R1-R6): accuracy declines consistently from 69.43% at R1 (mean 220 words) to 41.9% at R6 (mean 31.2 words), with the two-person speed section most sensitive to token reduction. These results demonstrate that CoT distillation improves compact student models and that response length is a critical factor in mathematical reasoning quality.

The alignment of language models is typically studied through the lens of capability benchmarks, but the dynamics of how models change during post-training remain poorly understood. We argue that the physical sciences, and thermodynamic phase-transition theory in particular, offer a principled and underexplored vocabulary for reasoning about these dynamics. As a case study, we instantiate this position through the lens of material Crystallization, which is a well-studied thermodynamic phase transition. For tasks like random number generation, this breaks into 3 phases: (1) the high entropy liquid phase in the pretrained model, with many distinct sampling distributions promptable from the model; (2) the nucleation phase caused by supervised finetuning, in which behavior collapses onto a single seed distribution present in the pretrained LLM; and (3) a settling phase in which reinforcement learning techniques redistribute probability of the collapsed distribution, but largely keep it concentrated on the same options as the seed distribution. We propose intuitive metrics to verify the transitions between these phases, and validate the idea across a range of random tasks. Crystallization is one instance of a broader class of physical frameworks we believe alignment research should import to answer questions about where alignment-induced structure comes from, why it converges where it does, and what it fundamentally cannot change.

Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles. We present an end-to-end RLAIF (Reinforcement Learning from AI Feedback) framework to generate \emph{portable} job search queries, terms that abstract away seeker-specific identifiers while preserving generalizable qualifications. This task introduces a highly adversarial reward surface where policy optimization frequently exploits flaws in LLM-as-judge rubrics, resulting in degenerate verbatim-copying behaviors. We conducted comprehensive empirical experiments to isolate the impact of optimization mechanics against structured reward engineering. Our results demonstrate that for critic-free optimizers, performance is overwhelmingly dictated by robust reward shaping, rendering the specific choice of algorithm largely immaterial. While critic-free per-rollout baseline methods (RLOO and REINFORCE++) natively resist reward-hacking, the group-relative advantage normalization in GRPO appears uniquely sensitive to spurious reward signals, making it disproportionately susceptible to exploitation. We show that introducing a deterministic, rule-based reward floor to correct for rewards assigned to verbatim copying mitigates this failure mode, resulting in a substantial $+0.147$ quality improvement on a cross-family evaluation judge. Ultimately, we show that the training-time reward model inflates performance gains by $2.4\times$, confirming that the training success is fundamentally dependent on enforcing reward-shaping disciplines rather than selecting alternative optimizers.

Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness. In this paper, we present a red teaming framework that systematically uncovers vulnerabilities in LLM outputs. Our approach employs a novel multi-role architecture comprising target, attacker, and jury models. The attackers generate increasingly effective adversarial prompts while the jury rigorously evaluates response accuracy and consistency across tasks. In a case study, our strategy proved particularly effective at exposing unfaithfulness in LLM responses. Exploitative adversarial prompts increased the attack success rate by up to 7.9% in question-answering tasks, revealing weaknesses in reliability. The approach identifies how structural constraints in summarization can shape vulnerability patterns, with format limitations yielding measurable gains in faithfulness, and shows that architectural design choices typically outweigh parameter scaling in determining model safety. The framework's key strength is its adaptability across evaluation tasks, from English question-answering to Arabic summarization, enabling comprehensive comparison of model vulnerabilities. While it excels at comparing cross-model and cross-linguistic vulnerabilities, it faces challenges in fully automating adversarial prompt generation across languages. Our experiments also reveal limitations in detecting subtle forms of unfaithfulness that do not manifest as explicit factual contradictions, particularly across linguistic contexts. Overall, this architecture provides both actionable insights into current LLM vulnerabilities and a scalable methodology for ongoing safety evaluation as models evolve.

When a benchmark's accuracy saturates, it is often retired and replaced with a more challenging version. We show that this approach privileges accuracy and misses the opportunity to study six other key dimensions of agent performance: construct validity issues such as shortcuts, out-of-distribution generalizability, efficiency, reliability, the relative importance of the model versus the scaffold, and uplift from human-agent collaboration. We use CORE-Bench Hard, a benchmark for computational reproducibility of scientific code, as a case study to demonstrate that measuring agents along these dimensions yields meaningful insights into agent performance even after accuracy saturates. First, we surface threats to construct validity in CORE-Bench Hard that are difficult to anticipate with less capable agents. We introduce an improved benchmark, CORE-Bench v1.1, and an out-of-distribution task suite, CORE-Bench OOD. Second, we find that despite accuracy saturation, CORE-Bench v1.1 remains useful for measuring efficiency, reliability, model performance, and scaffold performance. Finally, we conduct a small-scale randomized experiment to measure uplift from human-agent collaboration on real-world computational reproducibility tasks. We find a statistically significant speedup by about a factor of two -- likely underestimated due to one-fifth of human-only reproductions reaching the time limit before completing -- and describe various other findings. Together, our contributions present a more rigorous alternative to the dominant accuracy-centric evaluation paradigm.

Incidents in chemical plants can pose a high level of risk and harsh environments for first responders. Contamination and explosion hazards can deny human access to the affected infrastructure, underscoring the need for capable robot systems. This field report documents the successful deployment of a robotic task force to neutralize an explosive gas hazard at a chemical plant after a fire incident. An Unmanned Ground Vehicle (UGV) with a custom manipulation tool opened a critical valve under hazardous conditions, averting the threat of a large-scale explosion. We provide insights into robot deployment and use the mission results to highlight both the importance of rescue robotics and limitations of using research platforms in real emergency deployments, such as communication constraints and the need for enhanced operator-assistance functions.

Large language models (LLMs) are increasingly used to support software development, but their practical usefulness in applied game-development settings remains underexplored, especially when generated code must be integrated into an existing game software system. This paper presents an exploratory empirical case study of GPT-4o in a custom Python/Pygame endless runner. The study examines six selected development tasks: three localized refactoring tasks and three tasks involving gameplay feature generation. The resulting implementations were evaluated using software metrics, unit tests, and manual gameplay assessments. In this case study, all three selected refactoring tasks were completed successfully in functional terms, whereas only one of the three selected gameplay feature generation tasks resulted in a correctly integrated feature. The findings suggest that, in this setting, GPT-4o handled localized transformations more reliably than tasks requiring new gameplay interactions across multiple existing systems. Given the exploratory single-case design, these results are best interpreted as indicative observations rather than as generalizable evidence of category-level model performance. Overall, the paper contributes a transparent case-based account of the opportunities and limitations of LLM-assisted refactoring and gameplay feature generation in an existing game software system.

This paper presents a methodology-centered transfer learning framework for fragility adaptation under domain shift, class imbalance, and scarce target labels while preserving engineering interpretability and supporting decision-making under uncertainty. Four transfer learning strategies (instance-based, parameter-based, hierarchical Bayesian, and multi-source) are demonstrated through three complementary case studies: (i) instance-based transfer learning via importance weighting, demonstrated on coastal bridge fragility using Hurricane Katrina observations; (ii) parameter-based transfer learning together with hierarchical Bayesian transfer learning, enabling partial pooling across strata and posterior uncertainty quantification, demonstrated on residential building fragility using Hurricane Ian observations; and (iii) multi-source transfer learning that fuses multiple analytical fragility models with learned source weights and regularized target-domain adaptation, demonstrated on seismic bridge fragility using observations from the 2001 Nisqually earthquake. Across these case studies, direct transfer of source models (i.e. using existing state-of-the-art models) fails under domain shift and severe class imbalance, while targeted adaptation substantially improves failure detection and predictive stability in low-data regimes. These findings highlight the need for systematic guidance on diagnostics, strategy selection, and uncertainty reporting when developing and adapting fragility models.

Process twins provide real-time representations of entire production processes. By capturing how process steps interact, rather than monitoring a single machine in isolation as an asset-based digital twin does, they have the potential to drive efficiency gains across the whole process. However, developing a process twin is costly. It requires accurately modelling the entire production process: its process steps, the equipment and product-specific settings each step uses, and its process variations. The resulting model must then be bound to live operational data. We present FacProcessTwin, a system that leverages a large language model (LLM) to reduce this development time, building a process twin from a plant's process documentation and natural-language input from an operator. FacProcessTwin generates this complete process model and then automatically binds its process steps to live operational data. The generated model and its data bindings are rendered as an interactive process diagram through which manufacturing personnel can monitor and correct the system's autonomous decisions, such as resolving uncertainty at safety-critical binding steps. We evaluate FacProcessTwin through a real-world case study of an Australian food manufacturer, covering 16 production process flows that span chilled, frozen, and aseptic shelf-stable product categories and include process variations within the same product. The results show that FacProcessTwin generates these process models accurately (a mean F1 of 95.2% against ground truth) and builds each twin in roughly a sixth of the manual time. Its human-in-the-loop governance then keeps the safety-critical bindings correct: at ambiguous tags where a single-pass baseline silently mis-binds 75.0% of the time, FacProcessTwin defers to the operator and mis-binds none.

This study introduces enhancements to physics-constrained neural networks (PCNNs) that improve the accuracy and stability of hybrid short-term weather forecasting models. Building on the WeatherGFT architecture, three innovations are proposed. First, an upgraded numerical solver, combining a fifth-order weighted essentially non-oscillatory scheme (WENO-5), a beta-plane approximation, and subgrid-scale viscosity, permits a fourfold increase in the integration time step to 1200 s while reducing the daily mean squared error by up to 26%. Second, a unified autoregressive hybrid block replaces the original chain of 24 specialised modules, eliminating overfitting to specific lead times. Third, the physical core is integrated with two state-of-the-art neural backbones, resulting in PI-PredFormer and PI-IAM4VP. Evaluation on the WeatherBench South Pacific subset from 2000 to 2004 shows that these hybrids reduce root mean squared error at 1-12 h lead times by 8-22% compared to purely neural counterparts, while better preserving physical consistency. These results demonstrate that incremental refinement of hybrid components offers a practical route toward more accurate and efficient short-range weather forecasting.

Large language models can often close proof gaps in interactive theorem provers, but a verified theorem is not the same thing as a reusable library contribution. We study this distinction through a detailed case study: a semi-autonomous formalization of Grothendieck's vanishing theorem. The initial version compiles with no sorries, but an expert review found serious problems in definitions, theorem generality, file organization, and the API. We then ran a review-driven refactor and compression process and obtained a second expert review. The before-and-after comparison shows a sharp split: agents adapted well to local, mechanically checkable feedback, but remained weak at choosing definitions and designing APIs. We argue that autoformalization should be evaluated not only by closed sorries, but by whether the resulting formalization survives expert review.

Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets. We study an auditable staged-promotion protocol for a fixed micro-pretraining runner on two heterogeneous host blocks: Windows A100 and Linux L40S. Starting from twelve prior-screened configurations, we use staged budgets of 2 minutes, 5 minutes, 10 minutes, 60 minutes, and 12 hours, with frozen promotion rules before expensive continuations. The early screens are intentionally treated as unstable: the 5- and 10-minute rankings are host-sensitive, and the eventual 12-hour top-ranked condition is not the mean-best condition at the replicated 10-minute gate. Because seed ranges differ across stages, these changes are operational promotion evidence, not within-seed curves. A replicated 60-minute gate keeps the Staged Factorial Screening bridge reference in the promoted set, where it ranks first in all four 60-minute host-seed cells. In the final 12-hour confirmation package, the bridge condition ranks first in all four host-seed cells across two seeds; the greedy comparator does not meet the frozen 0.010 val_bpb near-equivalence rule; and the cheaper d8/ar48 (depth-8, aspect-48) sentinel does not meet the frozen 0.020 mean-gap rule. The executed 12-hour branch spends 144 GPU-hours, and the full staged protocol records 169.2 training GPU-hours including screening stages. Continuing all four 60-minute candidates would spend 192 GPU-hours, while continuing all nine replicated 10-minute candidates would spend 432 GPU-hours. The latter numbers are accounting counterfactuals for unrun continuations, not evidence that skipped candidates could not have overtaken the reference. The result is a bounded cost-allocation finding, not a claim of global optimality, capacity-normalized superiority, or superiority over adaptive hyperparameter optimization methods.

Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring different evaluation perspectives. In this demo, we present PROBE-Web, an interactive system for probing diverse evaluation landscapes for KGC models. PROBE-Web enables users to flexibly evaluate KGC models by adjusting two critical perspectives: (P1) predictive sharpness and (P2) popularity-bias robustness. Through a user-friendly GUI, users easily evaluate multiple KGC models and analyze their strengths and weaknesses. PROBE-Web provides four key functionalities: (1) conventional evaluation toolkit, (2) flexible perspective-aware evaluation, (3) explainable case studies, and (4) evaluation landscape exploration. We believe that PROBE-Web can help users better understand KGC models aligning with their objectives.

I report a case study in AI-paired software engineering: five working ports of a vector illustration application across Rust, Swift, OCaml, Python, and browser-based platforms, built by a single developer in approximately 120 evening hours. The methodology pairs AI-assisted implementation with two safeguards -- a precise executable YAML specification serving as the single source of truth, and parallel implementations functioning as a built-in differential-testing layer. The five ports share a 23{,}000-line specification; per-port native code ranges from 0 to roughly 95{,}000 lines, reflecting the specification's escape hatch. I argue that AI-paired engineering, conditional on these two safeguards, makes feasible scope of work that conventionally requires multiple developer-years, and frame the methodology as a revival of N-version programming, a 1980s approach abandoned on cost grounds that AI changes. The paper reports concrete artifacts and honest limitations of the single-developer case study.

Agentic AI tools offer a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain experts days to months to build, where scientists care about correctness and robustness, not implementation details. We present an empirical study of general-purpose coding agents on a fly optogenetics data-to-discovery pipeline. We assess agents on tasks substantially larger than existing benchmarks, datasets orders of magnitude bigger, and evaluation criteria grounded in domain expert standards. We show that agents can solve several individual pipeline stages, suggesting stage-level automation is tractable. By analyzing agents' code iterations, we show that they struggle most when there is not a pre-defined criterion to iterate on, and they must instead use their scientific judgment to assess their current solution, a key open challenge. Mirroring scientific practice, they sometimes attempt visual inspection of intermediate outputs for self-evaluation, but largely fail to interpret what they see or act on it appropriately. Solving the end-to-end pipeline correctly requires stringing together successes across all pipeline stages, and this is beyond agents' current abilities. We identify challenges largely absent from existing benchmarks, including computational resource management and generalization to large held-out data collections. Finally, we distill principles for constructing scientific tasks and rigorous evaluation criteria for open-ended problems.

A mobile phone vibrating on a hard surface often sounds qualitatively unlike ordinary audiovisual recordings when reproduced through laptop loudspeakers. We propose that part of this perceptual distinctiveness can be described as a nested periodicity: a first-order cepstral structure reflecting the vibration period and its multiples, and a second-order cepstral structure reflecting repeated spacing within the first-order cepstrum. Treating the perceptual effect as real and using a deliberately transparent synthetic signal chain, we model six stages: mechanical generation, surface and air propagation, microphone capture, encoding and decoding, laptop-speaker playback, and re-recording or post-processing. The synthetic analysis shows that the first-order cepstral periodicity is preserved across the chain, whereas a cleaner bimodal or quasi-bimodal second-order cepstral signature is most evident at the mechanical source and at laptop-speaker playback. The result supports, but does not prove, the hypothesis that laptop reproduction can re-emphasize a latent contact-vibration periodicity that is less cleanly expressed in intermediate recorded and encoded forms. We frame second-order cepstral bimodality as an exploratory descriptor of contact-vibration playback rather than as a completed perceptual metric. Required validation includes recordings of real devices, controlled playback transfer functions, perceptual judgments, and comparisons against ordinary speech, music, and environmental recordings.

We present our ongoing work on the veriFIRE project: a collaboration between industry and academia, aimed at applying verification to increase the reliability of a real-world, safety-critical system. Specifically, we target an airborne platform for wildfire detection, which incorporates two deep neural networks. We present an end-to-end methodology for verifying \textit{consistency properties} in this system. Our approach encodes application-grounded requirements into solver-compatible queries for existing neural network verifiers. We study properties of interest over critical operational scenarios: (i) monotonicity of detector confidence as target intensity increases; and (ii) bounded detector response under physically plausible blur over the sensor. We instantiate these encodings using state-of-the-art neural network verification backends and evaluate them at scale on real background samples. For the first property, all verification queries are solved in under five minutes. For the second property, verification is substantially harder, highlighting key scalability challenges for richer, higher-dimensional specifications. Overall, the results demonstrate that meaningful, domain-specific guarantees can be obtained for industrial systems.

High-stakes production document-generation systems require language models to be adaptive, evidence-grounded, and auditable. We present HOPM, a hierarchical online prompt mutation framework evaluated on a real marketplace dispute-evidence workflow. HOPM treats prompts as online policies: a family/version router selects a prompt, deterministic guardrails attribute failures to mutable prompt-token categories, and dual feedback from human review and an automated judge updates both routing and mutation priorities. The primary evidence is an observed matched production-evaluation ablation: seven variants are evaluated on the same 600 cases each, enabling component comparisons against static prompting, manual iteration, bandit-only routing, mutation-only adaptation, human-only feedback, auto-judge-only feedback, and full dual-loop HOPM. Full HOPM improves count win rate over a static control from 34.7% to 45.7% (+11.0 pp; paired McNemar p = 1.31e-11) and amount-weighted win rate from 22.3% to 41.4% (+19.1 pp; 95% paired bootstrap CI [10.3, 28.9] pp). It also increases mean Likert quality from 3.18 to 4.40 and reduces issue-flag rate from 15.3% to 5.2%. Supporting review artifacts cover 770 generated-text reviews, 318 labeled reviewer exports, a 10-case/61-rating calibration slice, and a 70-case/350-rating OCR benchmark; these artifacts calibrate rubric, guardrail, title-risk, and OCR-risk interpretation rather than substituting for the production ablation. The paper includes control setup, sample sizes, confidence intervals, paired tests, prompt-token categories, pseudocode, schema, rubric, guardrail taxonomy, and a constructed example so the evaluation structure can be reproduced without exposing proprietary evidence.

Ship finance is a data-intensive and document-heavy segment of asset-based lending, requiring the integration of financial, technical, contractual, and regulatory information from heterogeneous and largely unstructured sources. Increasing environmental regulation and ESG reporting requirements are adding further complexity to underwriting and loan-origination processes. Recent advances in artificial intelligence (AI), particularly large language models (LLMs), create new opportunities for processing and analysing such information. This paper reviews potential applications of AI in ship finance, with a particular focus on LLM-based systems for document comprehension, information extraction, and workflow automation. We present ShipFinance.ai, a modular agentic architecture to support loan application workflows in ship finance. The proposed system combines an LLM-based extraction module, financial analysis components, external maritime data services, and a controlled document-generation module with a chatbot interface to support the preparation of standardized financing applications. The paper discusses the key challenges for using such models in production. We argue that AI-assisted systems can support maritime finance professionals in managing increasingly complex information and reporting requirements.

User Experience Research (UXR) Points of View (POVs) distil complex and often fragmented research evidence into actionable perspectives that guide how teams interpret user needs, frame design decisions, and align stakeholders. Although POVs are widely used in industry practice, there are few published examples that explicitly document how POVs are constructed, particularly in culturally sensitive and low-resource contexts. This paper presents an exemplar case study demonstrating how a culturally grounded, AI-augmented UXR POV was developed to inform TeleDeCa, a telemedicine dementia care framework for family caregivers in Nigeria. Building on the UXR POV Playbook and pyramid framework, we illustrate how mixed-methods research, hypothesis generation, and ontology-based modelling can be combined to form a defensible POV without requiring a fully finalised system or validated outcomes. Generative AI (GenAI) is integrated across the UXR POV framework as a bounded research collaborator, supporting synthesis, hypothesis exploration, and narrative construction while preserving human judgment, ethical accountability, and cultural sensitivity. The contribution of this paper lies in the extraction of reusable Play Cards and a Play that extend the UXR POV Playbook and serve as exemplar material for the CHI 2026 workshop on developing AI-powered UXR POVs.

Urban villages, the widespread informal settlements which have emerged as a result of rapid urbanization, are now major residential hubs for migrant workers in large cities in China. The dense arrangement of buildings in these areas often leads to unreliable GPS signals, while incomplete mapping data further impairs accurate route planning and navigation. These issues not only hinder everyday mobility but also pose significant challenges for emergency response, as confusing road layouts and GPS inaccuracies can complicate evacuation efforts. To address these challenges, we propose a practical vision-based geo-localization solution tailored for dense urban environments. Our approach features a low-cost data collection pipeline utilizing a dual-camera system, comprising a panoramic camera and a smartphone camera, to capture synchronized 360-degree panoramas and query images. Using Shipai Village, a well-known densely populated urban village in Guangzhou, as a case study, we develop a specialized image geo-localization dataset. We then assess and compare the performance of existing models across various scene types to identify their strengths and weaknesses. The findings demonstrate both the potential and limitations of visual-based localization in dense urban-village environments. Our framework aims to enhance pedestrian navigation, last-mile delivery, and emergency management in areas with poor GPS coverage, ultimately supporting the vulnerable populations living within these informal settlements.

Are AI agents tools, co-authors, or researchers? We present a quantified case study ($N=1$): a physicist supervising an AI coding agent (Claude Code, Sonnet and Opus models) over 12 work days and 57 sessions to build CLAX-PT, a differentiable one-loop perturbation theory module in JAX. We documented and classified 15 supervision events by intervention level. The agent resolved ten autonomously by iterating against oracle tests. Two more by the physicist's domain knowledge. The three it could not -- all evaded oracle detection -- share a common property: the agent treated symptom reduction as root-cause resolution. It spent 33 of the 57 sessions adjusting coefficients within a code architecture that could not represent the target physics, and could not re-evaluate its CLASS-PT branch choice even when prompted to reconsider; only an injected physics concept (anisotropic BAO damping) triggered the redesign. Separately, the agent committed a calibrated correction that passed all oracle tests but corresponded to no quantity in the theory, predicting wrong values at any other cosmology. The fudge factor was caught and replaced within the same session. Three supervision practices proved critical for catching what oracle tests missed: testing at diverse parameter points beyond the fiducial calibration; shared changelogs that surfaced stalled exploration across sessions; and an explicit rule against unphysical numerical patches. In this case, supervision design, not model capability, determined whether the agent's output was trustworthy. Closing the gap would require agents that propose architectural alternatives rather than optimize within a given structure, and distinguish predictive adequacy from explanatory correctness -- capabilities not exhibited here, not obviously addressed by scaling alone. [Abridged.]

The purpose of this article is to provide validation to my deep neural network alternative in the context of LLMs. Very recently, there has been a significant interest by Chinese researchers in a model called RBF network, as a substitute to standard DNNs, with increased explainability and higher accuracy. It turns out that my new model, discovered independently, is based on the exact same machinery. But with a major twist: it does not need DNN as it finds the global optimum of the loss function in closed form, in one iteration, thus eliminating the tedious training step. Here I provide a high-level overview of my technology, with case study and comparison to similar methods.

We introduce interaction SSD, an extension of Supervised Semantic Differential that models how semantic meaning varies across moderators such as groups, traits, or conditions making this variation testable and interpretable. The method estimates a main semantic gradient, an interaction gradient, and conditional gradients, all interpretable through standard SSD tools. We illustrate it on the UC Berkeley Measuring Hate Speech corpus, testing whether annotator racial identity moderates hate-speech judgments of comments targeting people of color. The interaction model detects a significant moderation effect: the shared gradient contrasts dehumanizing hostility with counter-speech, while the interaction gradient reveals smaller group-linked differences in which semantic cues predict hate-speech ratings. Interaction SSD makes moderated meaning-outcome relationships statistically testable and interpretable.

Large Language Models (LLMs) are increasingly deployed in diverse cultural contexts, yet their ability to master aesthetic stylistics, i.e., the strategic use of language to evoke cultural resonance, remains underexplored. We curate C4STYLI, a benchmark of highly stylized translated movie titles and advertising slogans from Hong Kong and the Chinese Mainland, to evaluate LLMs via the lens of behavioral recognition and productive competence. Extensive evaluations show that LLMs differ from humans in stylistic recognition, and this recognition ability varies across text domains. In addition, stylistic recognition and generation performance in LLMs are not consistently aligned. To further examine whether LLMs genuinely capture stylistic information in stylistic recognition, we conduct structural ablation with logistic regression probes. We find that, in the Hong Kong setting, stylistic recognition in LLMs relies primarily on surface-level linguistic information rather than stylistic structure. This suggests limited sensitivity to Hong Kong-specific stylistic structure.

Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens when an agent is embedded persistently in a real academic research environment with durable memory, local files, external tools, scheduled routines, delegated roles, and explicit safety protocols. Methods: A structured self-observed implementation case study was conducted from January 31 to May 25, 2026. The unit of analysis was the persistent human-agent environment: researcher, agent runtime, memory layer, tools, repositories, scheduled jobs, specialized agent roles, and governance rules. Outcomes were organized using PARE-M (Persistent Agentic Research Environment Measurement), a measurement framework covering architecture, utilization, artifact production, resource use, reproducibility, and governance. Results: Recoverable main-agent telemetry contained 75,671 de-duplicated records across 96 active days, with 8,059 user-role and 23,710 assistant-role messages. The workspace included 502 memory-related files, 17 configured agent directories, and 57 skill files. Active system time was 579.7 hours (30-minute capped-gap estimate). Memory-derived records identified 482 output-proxy events and 889 failure, verification, correction, or protocol-proxy events. A strict May 2026 trajectory subset captured 627 model-completed events and 73.95 million recorded tokens, of which 82.9% were cache reads. Conclusions: The workflow was cache-dominant, suggesting that persistent agentic environments may shift the economic unit from cost per token to cost per completed artifact. Future evaluations should use artifact-level denominators, reproducible parsing rules, correction taxonomies, and independent coding of governance events.

Scientific knowledge is increasingly dispersed across vast and heterogeneous scientific literature, where important claims are often implicit, evolving, and internally debated. While large language models (LLMs) have shown impressive performance in information extraction and summarization, their ability to recover latent scientific consensus remains unclear. Here, we investigate this problem in the context of high-temperature superconductivity (HTS), a long-standing and highly debated topic in condensed matter physics, as a challenging testbed. Using near 18,000 highly-cited publications over the past seven decades, we construct a structured knowledge graph linking competing superconducting mechanisms, material families, evidential modalities, and citation relations. We find that LLM-extracted representations recover coherent and physically interpretable structures, including family-dependent mechanism profiles, evidence-specific correlations, and citation-mediated temporal evolution of scientific beliefs. Ablation studies on LLM further show that the global structure remains robust across prompting, decoding, and model variations. Our results suggest that LLMs can indeed serve as scalable tools for deciphering scientific knowledge in domains characterized by competing interpretations and evolving knowledge.

We study the symmetric polynomial $\prod_{α\in A_{n,d}}\bigl(1+α_1 x_1+\cdots+α_n x_n\bigr)$ where $A_{n,d}:=\{α\in\mathbb{Z}_{\ge 0}^n:|α|=d\}$, which is the total Chern class of $\mathrm{Sym}^d(\mathbb{C}^n)$, viewed as a torus representation whose Chern roots are the weights $α_1 x_1+\cdots+α_n x_n$ for $α\in A_{n,d}$. Its homogeneous degree-$k$ part $c_k(n,d)$ is the $k$-th Chern class of $\mathrm{Sym}^d(\mathbb{C}^n)$. These Chern classes, together with their coefficients in various symmetric function bases, play a central role in enumerative geometry. Despite their simple definition, general closed formulas for their coefficients are subtle, and many structural properties of these classes have remained poorly understood. In this paper we prove several conjectures concerning their structure, establish explicit formulas, and study log-concavity properties for both the Chern classes and their $K$-theoretic analogue. In rank two, passing to the Schur basis and expanding the Schur coefficients in the binomial basis of $d$, we uncover a new binomial log-concavity phenomenon and prove refined positivity results. The paper demonstrates a novel methodology: we combine several AI systems with human mathematical insight in a coordinated workflow, deploying each tool according to its strengths in experimental discovery, conjecture formation, symbolic proof construction, and verification. To our knowledge, this is one of the first detailed case studies of orchestrating multiple AI tools to make substantial progress on a coherent mathematical research project.